You or the agent? A battery on the Romanian day-ahead market
You run a 2 MWh battery on the Romanian day-ahead electricity market. Each card is a real day of 2025 or 2026. Like the agent of the lecture, you plan the day before its prices are known: you see only yesterday's 24 hourly prices and choose one of four simple plans. Then you see what your plan, the agent and a trader with perfect foresight earned on that day's real prices.
The battery charges or discharges 1 MWh of stored energy per hour, starts the day empty and loses 15% of the energy over a full cycle (85% round-trip efficiency). The agent is the tabular Q-learning agent of the lecture (reinforcement learning: it learned which hours to charge and discharge from 1,746 days of 2019-2023); its state is the hour, the stored energy and the rank of that hour among yesterday's prices. A card is won against the agent when your plan earns at least as much as the agent; the score counts the cards on which you chose the best of the four plans.
What the game shows
- Over the 638 test days (1 January 2025 to 24 October 2026), perfect foresight earns 202.1 thousand EUR, yesterday's optimal plan 163.1 thousand (80.7% of the maximum), tabular Q-learning 115.2 thousand (57.0%) and the deep Q-network (DQN) 101.3 thousand (50.1%), means of five seeds.
- The three fixed plans of the game earn 77.2 (night to evening), 144.9 (midday to evening) and 148.0 thousand EUR (two cycles) on the same days; the agent of the game (first seed) earns 101.4 thousand.
- A simple rule that uses all 24 of yesterday's prices beats both learning agents: reinforcement learning must always be benchmarked against the rule already in use.
Data: hourly day-ahead prices for Romania, energy-charts.info (Fraunhofer Institute for Solar Energy Systems, ISE), up to 31 October 2026; hours in Central European Time (CET). The 40 days of the game are drawn at random from the 638 test days (seed 20261108); every game draws 8 of them. The hours of the fixed plans come from the mean price profile of 2019-2024. Code: lectures/L10/make_game_L10.py.

